EUVIMEDEUVIMED entdecken
Crossref

When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data

Rongjia Zheng, Qing Zhang, Yongwei Nie, Wei-Shi Zheng

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (10) · 10599-10607

DOI: 10.1609/aaai.v39i10.33151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Rongjia Zheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a framework that achieves shadow removal by learning intrinsic image decomposition (IID) from unpaired shadow and shadow-free images. Although it is well-known that intrinsic images, \ie, illumination and reflectance, are highly beneficial to shadow removal, IID is rarely adopted by previous work due to its inherent ambiguity and the scarcity of training data. However, we find that by properly coupling shadow removal and IID into a joint learning framework, they can reinforce each other and enable promising results on both tasks, even with unpaired training data. Our framework is comprised of an IID network for separating the shadow input image into illumination and reflectance, and an illumination recovery network for predicting shadow-free illumination with which we are able to produce the shadow removal output by recombining with the estimated reflectance. We perform extensive experiments on various benchmark datasets to demonstrate the effectiveness of our method in shadow removal, and also showcase our advantage over previous IID methods in handling images with complex shadows.

Zitieren

APA

Zheng, R., Zhang, Q., Nie, Y., & Zheng, W. (2025). When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data. Proceedings of the AAAI Conference on Artificial Intelligence, 39(10), 10599-10607. https://doi.org/10.1609/aaai.v39i10.33151

Vancouver

Zheng R, Zhang Q, Nie Y, Zheng W. When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(10):10599-10607. doi:10.1609/aaai.v39i10.33151

BibTeX
@article{Zheng2025,
  author = {Zheng, Rongjia and Zhang, Qing and Nie, Yongwei and Zheng, Wei-Shi},
  title = {When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {10},
  pages = {10599--10607},
  doi = {10.1609/aaai.v39i10.33151}
}
Kostenlos starten →